Browse > Article
http://dx.doi.org/10.9708/jksci.2021.26.04.047

Multiple Binarization Quadtree Framework for Optimizing Deep Learning-Based Smoke Synthesis Method  

Kim, Jong-Hyun (School of Software Application, Kangnam University)
Publication Information
Journal of the Korea Society of Computer and Information / v.26, no.4, 2021 , pp. 47-53 More about this Journal
Abstract
In this paper, we propose a quadtree-based optimization technique that enables fast Super-resolution(SR) computation by efficiently classifying and dividing physics-based simulation data required to calculate SR. The proposed method reduces the time required for quadtree computation by downscaling the smoke simulation data used as input data. By binarizing the density of the smoke in this process, a quadtree is constructed while mitigating the problem of numerical loss of density in the downscaling process. The data used for training is the COCO 2017 Dataset, and the artificial neural network uses a VGG19-based network. In order to prevent data loss when passing through the convolutional layer, similar to the residual method, the output value of the previous layer is added and learned. In the case of smoke, the proposed method achieved a speed improvement of about 15 to 18 times compared to the previous approach.
Keywords
Quadtree; Binarization; Downscaling; Convolutional neural network; Super-resolution; Fluid simulations;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Jing, Yongcheng, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, and Mingli Song. "Neural style transfer: A review." IEEE transactions on visualization and computer graphics, 2019. DOI: 10.1109/tvcg.2019.2921336   DOI
2 Azadi, Samaneh, Matthew Fisher, Vladimir G. Kim, Zhaowen Wang, Eli Shechtman, and Trevor Darrell. "Multi-content gan for few-shot font style transfer." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7564-7573. 2018. DOI: 10.1109/CVPR.2018.00789   DOI
3 Sun, Y.S., Wan, L., Gan, Y., Wang, J.G. and Jiang, C.M., "Design of motion control of dam safety inspection underwater vehicle." Journal of Central South University, 19(6), pp.1522-1529, 2012. DOI: 10.1007/s11771-012-1171-6   DOI
4 Oshita, Masaki, and Akifumi Makinouchi. "A dynamic motion control technique for human-like articulated figures." In Computer Graphics Forum, vol. 20, no. 3, pp. 192-203. Oxford, UK and Boston, USA: Blackwell Publishers Ltd, 2001. DOI: 10.1111/1467-8659.00512   DOI
5 Liu, X., Zhou, S., Gao, Y., Hu, H., Liu, Y., Gui, C. and Liu, S., "Numerical simulation and experimental investigation of GaN-based flip-chip LEDs and top-emitting LEDs". Applied Optics, 56(34), pp.9502-9509, 2017. DOI: 10.1364/AO.56.009502   DOI
6 Kun Zhou, Minmin Gong, Xin Huang, Baining Guo, "Data-Parallel Octrees for Surface Reconstruction", IEEE Transactions on Visualization and Computer Graphics (TVCG), Volume 17, Issue 5, page 669-681, 2011. DOI: 10.1109/TVCG.2010.75   DOI
7 Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger, "OctNet: Learning Deep 3D Representations at High Resolutions", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), arXiv:1611.05009v4, 2017. DOI: 10.1109/CVPR.2017.701   DOI
8 Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong, "O-CNN: octree-based convolutional neural networks for 3D shape analysis", ACM Transactions on Graphics, Volume 36, Issue 4, Article No. 72, 2017. DOI: 10.1145/3072959.3073608   DOI
9 Kim, T., Thurey, N., James, D. and Gross, M., "Wavelet turbulence for fluid simulation". ACM Transactions on Graphics, vol. 27, issue 3, pp.1-6, 2008. DOI: 10.1145/1360612.1360649   DOI
10 Hong Byeongsun, Park Jihyeok, Choi Myungjin, Kim Changhun. "Quad Tree Based 2D Smoke Super-resolution with CNN". J Korea Computer Graphics Society, vol. 25, issue 3, pp. 105-113, 2019. DOI: 10.15701/kcgs.2019.25.3.105   DOI
11 Bargteil, A.W., Goktekin, T.G., O'brien, J.F. and Strain, J.A., "A semi-Lagrangian contouring method for fluid simulation". ACM Transactions on Graphics, vol. 25, issue 1, pp.19-38, 2006. DOI: 10.1145/1122501.1122503   DOI
12 Xiao X, Zhou Y, Wang H, Yang X. "A novel cnn-based poisson solver for fluid simulation". IEEE Transactions on Visualization and Computer Graphics, 2018. DOI: 10.1109/TVCG.2018.2873375   DOI
13 Setaluri, R., Aanjaneya, M., Bauer, S. and Sifakis, E., "SPGrid: A sparse paged grid structure applied to adaptive smoke simulation". ACM Transactions on Graphics, vol. 33, issue 6, pp.1-12, 2014. DOI: 10.1145/2661229.2661269   DOI
14 Losasso, Frank, Frederic Gibou, and Ron Fedkiw. "Simulating water and smoke with an octree data structure." In ACM SIGGRAPH 2004 Papers, pp. 457-462. 2004. DOI: 10.1145/1015706.1015745   DOI
15 McAdams, Aleka, Eftychios Sifakis, and Joseph Teran. "A Parallel Multigrid Poisson Solver for Fluids Simulation on Large Grids." In Symposium on Computer Animation, pp. 65-73. 2010. DOI: 10.2312/SCA/SCA10/065-073   DOI
16 Tompson, Jonathan, Kristofer Schlachter, Pablo Sprechmann, and Ken Perlin. "Accelerating eulerian fluid simulation with convolutional networks." In International Conference on Machine Learning, pp. 3424-3433. PMLR, 2017.
17 Park H, Yu R, Lee Y, Lee K, Lee J. "Understanding the Stability of Deep Control Policies for Biped Locomotion". arXiv preprint arXiv:2007.15242. 2020.
18 Won, J., Park, J. and Lee, J., "Aerobatics control of flying creatures via self-regulated learning". ACM Transactions on Graphics, 37(6), pp.1-10, 2018. DOI: 10.1145/3272127.3275023   DOI
19 Lee, Jaedong, Jungdam Won, and Jehee Lee. "Crowd simulation by deep reinforcement learning." In Proceedings of the 11th Annual International Conference on Motion, Interaction, and Games, pp. 1-7, 2018. DOI: 10.1145/3274247.3274510   DOI
20 Chu, M. and Thuerey, N., "Data-driven synthesis of smoke flows with CNN-based feature descriptors". ACM Transactions on Graphics, 36(4), pp.1-14, 2017. DOI: 10.1145/3072959.3073643   DOI
21 Li, Jianan, Xiaodan Liang, Yunchao Wei, Tingfa Xu, Jiashi Feng, and Shuicheng Yan. "Perceptual generative adversarial networks for small object detection." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1222-1230. 2017. DOI: 10.1109/CVPR.2017.211   DOI
22 Huang, Wenqing, Mingzhu Huang, and Yuting Zhang. "Detection of traffic signs based on combination of GAN and faster-RCNN." In Journal of Physics: Conference Series, vol. 1069, no. 1, p. 012159. 2018. DOI: 10.1088/1742-6596/1069/1/012159   DOI
23 Shah, Maurya, Jonathan M. Cohen, Sanjit Patel, Penne Lee, and Frederic Pighin. "Extended galilean invariance for adaptive fluid simulation." In Proceedings of the 2004 ACM SIGGRAPH/Eur ographics symposium on Computer animation, pp. 213-221. 2004. DOI: 10.1145/1028523.1028551   DOI
24 Bulat, Adrian, Jing Yang, and Georgios Tzimiropoulos. "To learn image super-resolution, use a gan to learn how to do image degradation first." In Proceedings of the European conference on computer vision (ECCV), pp. 185-200. 2018. DOI: 10.1007/978-3-030-01231-1_12   DOI
25 Yang, C., Yang, X. and Xiao, X., "Data-driven projection method in fluid simulation". Computer Animation and Virtual Worlds, 27(3-4), pp.415-424, 2016. DOI: 10.1002/cav.1695   DOI
26 Kim, Byungsoo, Vinicius C. Azevedo, Nils Thuerey, Theodore Kim, Markus Gross, and Barbara Solenthaler. "Deep fluids: A generative network for parameterized fluid simulations." In Computer Graphics Forum, vol. 38, no. 2, pp. 59-70. 2019. DOI: 10.1111/cgf.13619   DOI
27 Xie, Y., Franz, E., Chu, M. and Thuerey, N., "tempoGAN: A temporally coherent, volumetric gan for super-resolution fluid flow". ACM Transactions on Graphics, 37(4), pp.1-15, 2018. DOI: 10.1145/3197517.3201304   DOI
28 Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, "Image Super-Resolution Using Deep Convolutional Networks", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, issue 2, pp. 295-307, 2016. DOI: 10.1109/TPAMI.2015.2439281   DOI